SlideShare a Scribd company logo
1 of 22
Download to read offline
Neural Computing
November 5, 2019
Amit Praseed Classification November 5, 2019 1 / 22
Introduction
Neural computing tries to model the working of neurons in a human
brain.
It is a subset of Artificial Intelligence, and represents one of the facets
of ”intelligence”.
Note that neural networks only try to model neurons, and are not
trying to replicate the functioning of a human brain.
Amit Praseed Classification November 5, 2019 2 / 22
How do neurons work?
A neuron is composed of three main parts - dendrites, axon and axon
terminals.
Neurons are connected end to end, i.e. the dendrites of a neuron are
connected to the axon terminals of another neuron to enable informa-
tion flow.
However, in between the axon terminals and the dendrites of the other
neuron, there is a gap which is called as synapse.
Electrical signals which flow through a neuron are passed on to the
next neurons through this synapse, which attenuates the signal.
By BruceBlaus - Own work, CC BY 3.0,Amit Praseed Classification November 5, 2019 3 / 22
The Perceptron
The simplest model of a neuron is the Perceptron.
A perceptron consists of n inputs x1, x2, ...xn which models the electrical
signals flowing through a neuron.
To model the attenuation across a synapse, each of these inputs are
multiplied by a weight w1, w2, ...wn.
So the total input that reaches the next neuron is x1w1 + x2w2 + ... +
xnwn.
The perceptron is said to ”fire” only if this input received exceeds a
threshold value or bias θ.
a(t) =
1, n
i=0 wi ∗ xi > 0
0, n
i=0 wi ∗ xi ≤ 0
where w0 = θ and x0 = 1 and η is the learning rate.
Amit Praseed Classification November 5, 2019 4 / 22
The Perceptron Update Rule
The weights of the perceptron are changed along the following rules
wi (t + 1) =
wi (t) + η ∗ xi , ExpectedOutput ≤ ObservedOutput
wi (t) − η ∗ xi , ExpectedOutput > ObservedOutput
Amit Praseed Classification November 5, 2019 5 / 22
The Perceptron
−2 −1 1 2
−2
−1
1
2
Let η = 0.2
Let W=


0
1
0.5


The line represented by the
weight vectors is
w0x0 + w1x1 + w2x2 = 0
x1 + 0.5x2 = 0
Amit Praseed Classification November 5, 2019 6 / 22
The Perceptron
−2 −1 1 2
−2
−1
1
2
Point:(1,1)
Weighted Input =
1x0+1x1+1x0.5=2.5>0
Activation: 1 (Correct Classifi-
cation)
Action: Do Nothing
Amit Praseed Classification November 5, 2019 7 / 22
The Perceptron
−2 −1 1 2
−2
−1
1
2
Point: (2,-2)
Weighted Input=1x0+1x2+
(-2)(0.5)=1>0
Activation: 1 (Incorrect Classi-
fication)
Update weight vectors:

w0
w1
w2

 =


0
1
0.5

 − η


1
2
−2

 =


−0.2
0.6
0.9


Amit Praseed Classification November 5, 2019 8 / 22
The Perceptron
−2 −1 1 2
−2
−1
1
2
Point: (2,-2)
Weighted Input=1x0+1x2+(-
2)(0.5)=1>0
Activation: 1 (Incorrect Classi-
fication)
Update weight vectors:

w0
w1
w2

 =


0
1
0.5

 − 0.2


1
2
−2

 =


−0.2
0.6
0.9


Amit Praseed Classification November 5, 2019 9 / 22
The Perceptron
−2 −1 1 2
−2
−1
1
2
Point: (-1,-1.5)
Weighted Input=1(-0.2)+
(-1)(0.6)+(-1.5)(0.9)<0
Activation: 0 (Correct Classifi-
cation)
Action: No Change
Amit Praseed Classification November 5, 2019 10 / 22
The Perceptron
−2 −1 1 2
−2
−1
1
2
Point: (-2,-1)
Weighted Input=1(-0.2)+
(-2)(0.6)+(-1)(0.9)<0
Activation: 0 (Correct Classifi-
cation)
Action: No Change
Amit Praseed Classification November 5, 2019 11 / 22
The Perceptron
−2 −1 1 2
−2
−1
1
2
Point: (-2,1)
Weighted Input=1(-0.2)+
(-2)(0.6)+(1)(0.9)=-0.5<0
Activation: 0 (Incorrect Classi-
fication)
Update weight vectors:

w0
w1
w2

 =


−0.2
0.6
0.9

 +
0.2


1
−2
1

 =


0
0.2
1.1


Amit Praseed Classification November 5, 2019 12 / 22
The Perceptron
−2 −1 1 2
−2
−1
1
2
Point: (-2,1)
Weighted Input=1(-0.2)+
(-2)(0.6)+(1)(0.9)=-0.5<0
Activation: 0 (Incorrect Classi-
fication)
Update weight vectors:

w0
w1
w2

 =


−0.2
0.6
0.9

 +
0.2


1
−2
1

 =


0
0.2
1.1


Amit Praseed Classification November 5, 2019 13 / 22
The Perceptron
−2 −1 1 2
−2
−1
1
2
Point: (1.5,-0.4)
Weighted Input=1(0)+
(1.5)(0.2)+(-0.4)(1.1)=-
0.14<0
Activation: 0 (Incorrect Classi-
fication)
Update weight vectors:

w0
w1
w2

 =


0
0.2
1.1

 +
0.2


1
1.5
−0.5

 =


0.2
0.5
1


Amit Praseed Classification November 5, 2019 14 / 22
The Perceptron
−2 −1 1 2
−2
−1
1
2
Point: (1.5,-0.4)
Weighted Input=1(0)+
(1.5)(0.2)+(-0.4)(1.1)=-
0.14<0
Activation: 0 (Incorrect Classi-
fication)
Update weight vectors:

w0
w1
w2

 =


0
0.2
1.1

 +
0.2


1
1.5
−0.5

 =


0.2
0.5
1


Amit Praseed Classification November 5, 2019 15 / 22
A Look Back at the Finale
−2 −1 1 2
−2
−1
1
2
Point: (-2,1)
Weighted Input=1(-0.2)+
(-2)(0.6)+(1)(0.9)=-0.5<0
Activation: 0 (Incorrect Classi-
fication)
Update weight vectors:

w0
w1
w2

 =


−0.2
0.6
0.9

 +
0.2


1
−2
1

 =


0
0.2
1.1


Amit Praseed Classification November 5, 2019 16 / 22
A Look Back at the Finale
−2 −1 1 2
−2
−1
1
2
Point: (-2,1)
Weighted Input=1(-0.2)+
(-2)(0.6)+(1)(0.9)=-0.5<0
Activation: 0 (Incorrect Classi-
fication)
Update weight vectors:

w0
w1
w2

 =


−0.2
0.6
0.9

 +
0.2


1
−2
1

 =


0
0.2
1.1


Amit Praseed Classification November 5, 2019 17 / 22
A Look Back at the Finale
−2 −1 1 2
−2
−1
1
2
Point: (1.5,-0.4)
Weighted Input=1(0)+
(1.5)(0.2)+(-0.4)(1.1)=-
0.14<0
Activation: 0 (Incorrect Classi-
fication)
Update weight vectors:

w0
w1
w2

 =


0
0.2
1.1

 +
0.2


1
1.5
−0.5

 =


0.2
0.5
1


Amit Praseed Classification November 5, 2019 18 / 22
A Look Back at the Finale
−2 −1 1 2
−2
−1
1
2
Point: (1.5,-0.4)
Weighted Input=1(0)+
(1.5)(0.2)+(-0.4)(1.1)=-
0.14<0
Activation: 0 (Incorrect Classi-
fication)
Update weight vectors:

w0
w1
w2

 =


0
0.2
1.1

 +
0.2


1
1.5
−0.5

 =


0.2
0.5
1


Amit Praseed Classification November 5, 2019 19 / 22
Widrow-Hoff Delta Rule
Modifying the weights by the input value during incorrect classification
seems excessive, and can lead to the decision boundary swinging back
and forth before stabilizing.
Intuitively, it is reasonable to modify the weights only by the difference
between the threshold and the weighted input.
wi (t + 1) = wi (t) + η∆xi (t)
∆ = θ −
n
i=0
wi ∗ xi
Note that in this way, there is no separate equation for the weighted
input lying on both sides of the threshold. The sign of ∆ automatically
takes care of this.
Amit Praseed Classification November 5, 2019 20 / 22
Widrow-Hoff Delta Rule
−2 −1 1 2
−2
−1
1
2
Point: (-2,1)
Weighted Input=1(-0.2)+
(-2)(0.6)+(1)(0.9)=-0.5<0
Activation: 0 (Incorrect Classi-
fication)
Update weight vectors:

w0
w1
w2

 =


−0.2
0.6
0.9

 +
(0.2)(0 − (−0.5))


1
−2
1

 =


−0.1
0.4
1


Amit Praseed Classification November 5, 2019 21 / 22
Widrow-Hoff Delta Rule
−2 −1 1 2
−2
−1
1
2
Point: (-2,1)
Weighted Input=1(-0.2)+
(-2)(0.6)+(1)(0.9)=-0.5<0
Activation: 0 (Incorrect Classi-
fication)
Update weight vectors:

w0
w1
w2

 =


−0.2
0.6
0.9

 +
(0.2)(0 − (−0.5))


1
−2
1

 =


−0.1
0.4
1


Amit Praseed Classification November 5, 2019 22 / 22

More Related Content

Similar to Perceptron Learning

Machine Learning.pdf
Machine Learning.pdfMachine Learning.pdf
Machine Learning.pdfnikola_tesla1
 
Neurvvvvvvvvvvvvvvvvvvvval Networks.pptx
Neurvvvvvvvvvvvvvvvvvvvval Networks.pptxNeurvvvvvvvvvvvvvvvvvvvval Networks.pptx
Neurvvvvvvvvvvvvvvvvvvvval Networks.pptxeman458700
 
Back Propagation in Deep Neural Network
Back Propagation in Deep Neural NetworkBack Propagation in Deep Neural Network
Back Propagation in Deep Neural NetworkVARUN KUMAR
 
Artificial Neural Network
Artificial Neural Network Artificial Neural Network
Artificial Neural Network Iman Ardekani
 
Classification using perceptron.pptx
Classification using perceptron.pptxClassification using perceptron.pptx
Classification using perceptron.pptxsomeyamohsen3
 
Deep learning simplified
Deep learning simplifiedDeep learning simplified
Deep learning simplifiedLovelyn Rose
 
latest TYPES OF NEURAL NETWORKS (2).pptx
latest TYPES OF NEURAL NETWORKS (2).pptxlatest TYPES OF NEURAL NETWORKS (2).pptx
latest TYPES OF NEURAL NETWORKS (2).pptxMdMahfoozAlam5
 
Data mining assignment 5
Data mining assignment 5Data mining assignment 5
Data mining assignment 5BarryK88
 
A hitchhiker’s guide to neuroevolution in Erlang
A hitchhiker’s guide to neuroevolution in ErlangA hitchhiker’s guide to neuroevolution in Erlang
A hitchhiker’s guide to neuroevolution in ErlangThoughtworks
 
Multilayer perceptron
Multilayer perceptronMultilayer perceptron
Multilayer perceptronsmitamm
 
Introduction to Artificial Neural Network
Introduction to Artificial Neural Network Introduction to Artificial Neural Network
Introduction to Artificial Neural Network Qingkai Kong
 
Introduction to Artificial Neural Networks - PART III.pdf
Introduction to Artificial Neural Networks - PART III.pdfIntroduction to Artificial Neural Networks - PART III.pdf
Introduction to Artificial Neural Networks - PART III.pdfSasiKala592103
 
Neural network
Neural networkNeural network
Neural networkmarada0033
 
Lecture 2: Artificial Neural Network
Lecture 2: Artificial Neural NetworkLecture 2: Artificial Neural Network
Lecture 2: Artificial Neural NetworkMohamed Loey
 

Similar to Perceptron Learning (20)

Artificial Neural Networks
Artificial Neural NetworksArtificial Neural Networks
Artificial Neural Networks
 
Machine Learning.pdf
Machine Learning.pdfMachine Learning.pdf
Machine Learning.pdf
 
Neurvvvvvvvvvvvvvvvvvvvval Networks.pptx
Neurvvvvvvvvvvvvvvvvvvvval Networks.pptxNeurvvvvvvvvvvvvvvvvvvvval Networks.pptx
Neurvvvvvvvvvvvvvvvvvvvval Networks.pptx
 
Back Propagation in Deep Neural Network
Back Propagation in Deep Neural NetworkBack Propagation in Deep Neural Network
Back Propagation in Deep Neural Network
 
Artificial Neural Network
Artificial Neural Network Artificial Neural Network
Artificial Neural Network
 
Classification using perceptron.pptx
Classification using perceptron.pptxClassification using perceptron.pptx
Classification using perceptron.pptx
 
Neural Networks
Neural NetworksNeural Networks
Neural Networks
 
CS767_Lecture_04.pptx
CS767_Lecture_04.pptxCS767_Lecture_04.pptx
CS767_Lecture_04.pptx
 
Deep learning simplified
Deep learning simplifiedDeep learning simplified
Deep learning simplified
 
latest TYPES OF NEURAL NETWORKS (2).pptx
latest TYPES OF NEURAL NETWORKS (2).pptxlatest TYPES OF NEURAL NETWORKS (2).pptx
latest TYPES OF NEURAL NETWORKS (2).pptx
 
lec04.pptx
lec04.pptxlec04.pptx
lec04.pptx
 
Data mining assignment 5
Data mining assignment 5Data mining assignment 5
Data mining assignment 5
 
A hitchhiker’s guide to neuroevolution in Erlang
A hitchhiker’s guide to neuroevolution in ErlangA hitchhiker’s guide to neuroevolution in Erlang
A hitchhiker’s guide to neuroevolution in Erlang
 
Multilayer perceptron
Multilayer perceptronMultilayer perceptron
Multilayer perceptron
 
Introduction to Artificial Neural Network
Introduction to Artificial Neural Network Introduction to Artificial Neural Network
Introduction to Artificial Neural Network
 
R package Recommendation Engine
R package Recommendation EngineR package Recommendation Engine
R package Recommendation Engine
 
Introduction to Artificial Neural Networks - PART III.pdf
Introduction to Artificial Neural Networks - PART III.pdfIntroduction to Artificial Neural Networks - PART III.pdf
Introduction to Artificial Neural Networks - PART III.pdf
 
Neural network
Neural networkNeural network
Neural network
 
DNN.pptx
DNN.pptxDNN.pptx
DNN.pptx
 
Lecture 2: Artificial Neural Network
Lecture 2: Artificial Neural NetworkLecture 2: Artificial Neural Network
Lecture 2: Artificial Neural Network
 

More from amitpraseed

Support Vector Machines (SVM)
Support Vector Machines (SVM)Support Vector Machines (SVM)
Support Vector Machines (SVM)amitpraseed
 
Principal Component Analysis
Principal Component AnalysisPrincipal Component Analysis
Principal Component Analysisamitpraseed
 
Introduction to Classification
Introduction to ClassificationIntroduction to Classification
Introduction to Classificationamitpraseed
 
Dimensionality Reduction
Dimensionality ReductionDimensionality Reduction
Dimensionality Reductionamitpraseed
 
Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networksamitpraseed
 
Bayesianclassifiers
BayesianclassifiersBayesianclassifiers
Bayesianclassifiersamitpraseed
 

More from amitpraseed (7)

Decision Trees
Decision TreesDecision Trees
Decision Trees
 
Support Vector Machines (SVM)
Support Vector Machines (SVM)Support Vector Machines (SVM)
Support Vector Machines (SVM)
 
Principal Component Analysis
Principal Component AnalysisPrincipal Component Analysis
Principal Component Analysis
 
Introduction to Classification
Introduction to ClassificationIntroduction to Classification
Introduction to Classification
 
Dimensionality Reduction
Dimensionality ReductionDimensionality Reduction
Dimensionality Reduction
 
Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networks
 
Bayesianclassifiers
BayesianclassifiersBayesianclassifiers
Bayesianclassifiers
 

Recently uploaded

How to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSHow to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSCeline George
 
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptxHMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptxEsquimalt MFRC
 
How to Add New Custom Addons Path in Odoo 17
How to Add New Custom Addons Path in Odoo 17How to Add New Custom Addons Path in Odoo 17
How to Add New Custom Addons Path in Odoo 17Celine George
 
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...Nguyen Thanh Tu Collection
 
REMIFENTANIL: An Ultra short acting opioid.pptx
REMIFENTANIL: An Ultra short acting opioid.pptxREMIFENTANIL: An Ultra short acting opioid.pptx
REMIFENTANIL: An Ultra short acting opioid.pptxDr. Ravikiran H M Gowda
 
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...Nguyen Thanh Tu Collection
 
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdfUGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdfNirmal Dwivedi
 
FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024Elizabeth Walsh
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfAdmir Softic
 
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...Pooja Bhuva
 
Wellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptxWellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptxJisc
 
Single or Multiple melodic lines structure
Single or Multiple melodic lines structureSingle or Multiple melodic lines structure
Single or Multiple melodic lines structuredhanjurrannsibayan2
 
Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Jisc
 
Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibitjbellavia9
 
General Principles of Intellectual Property: Concepts of Intellectual Proper...
General Principles of Intellectual Property: Concepts of Intellectual  Proper...General Principles of Intellectual Property: Concepts of Intellectual  Proper...
General Principles of Intellectual Property: Concepts of Intellectual Proper...Poonam Aher Patil
 
This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.christianmathematics
 
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptxMaritesTamaniVerdade
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsMebane Rash
 
SOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning PresentationSOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning Presentationcamerronhm
 
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptx
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptxCOMMUNICATING NEGATIVE NEWS - APPROACHES .pptx
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptxannathomasp01
 

Recently uploaded (20)

How to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSHow to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POS
 
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptxHMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
 
How to Add New Custom Addons Path in Odoo 17
How to Add New Custom Addons Path in Odoo 17How to Add New Custom Addons Path in Odoo 17
How to Add New Custom Addons Path in Odoo 17
 
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
 
REMIFENTANIL: An Ultra short acting opioid.pptx
REMIFENTANIL: An Ultra short acting opioid.pptxREMIFENTANIL: An Ultra short acting opioid.pptx
REMIFENTANIL: An Ultra short acting opioid.pptx
 
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
 
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdfUGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
 
FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
 
Wellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptxWellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptx
 
Single or Multiple melodic lines structure
Single or Multiple melodic lines structureSingle or Multiple melodic lines structure
Single or Multiple melodic lines structure
 
Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)
 
Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibit
 
General Principles of Intellectual Property: Concepts of Intellectual Proper...
General Principles of Intellectual Property: Concepts of Intellectual  Proper...General Principles of Intellectual Property: Concepts of Intellectual  Proper...
General Principles of Intellectual Property: Concepts of Intellectual Proper...
 
This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.
 
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan Fellows
 
SOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning PresentationSOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning Presentation
 
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptx
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptxCOMMUNICATING NEGATIVE NEWS - APPROACHES .pptx
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptx
 

Perceptron Learning

  • 1. Neural Computing November 5, 2019 Amit Praseed Classification November 5, 2019 1 / 22
  • 2. Introduction Neural computing tries to model the working of neurons in a human brain. It is a subset of Artificial Intelligence, and represents one of the facets of ”intelligence”. Note that neural networks only try to model neurons, and are not trying to replicate the functioning of a human brain. Amit Praseed Classification November 5, 2019 2 / 22
  • 3. How do neurons work? A neuron is composed of three main parts - dendrites, axon and axon terminals. Neurons are connected end to end, i.e. the dendrites of a neuron are connected to the axon terminals of another neuron to enable informa- tion flow. However, in between the axon terminals and the dendrites of the other neuron, there is a gap which is called as synapse. Electrical signals which flow through a neuron are passed on to the next neurons through this synapse, which attenuates the signal. By BruceBlaus - Own work, CC BY 3.0,Amit Praseed Classification November 5, 2019 3 / 22
  • 4. The Perceptron The simplest model of a neuron is the Perceptron. A perceptron consists of n inputs x1, x2, ...xn which models the electrical signals flowing through a neuron. To model the attenuation across a synapse, each of these inputs are multiplied by a weight w1, w2, ...wn. So the total input that reaches the next neuron is x1w1 + x2w2 + ... + xnwn. The perceptron is said to ”fire” only if this input received exceeds a threshold value or bias θ. a(t) = 1, n i=0 wi ∗ xi > 0 0, n i=0 wi ∗ xi ≤ 0 where w0 = θ and x0 = 1 and η is the learning rate. Amit Praseed Classification November 5, 2019 4 / 22
  • 5. The Perceptron Update Rule The weights of the perceptron are changed along the following rules wi (t + 1) = wi (t) + η ∗ xi , ExpectedOutput ≤ ObservedOutput wi (t) − η ∗ xi , ExpectedOutput > ObservedOutput Amit Praseed Classification November 5, 2019 5 / 22
  • 6. The Perceptron −2 −1 1 2 −2 −1 1 2 Let η = 0.2 Let W=   0 1 0.5   The line represented by the weight vectors is w0x0 + w1x1 + w2x2 = 0 x1 + 0.5x2 = 0 Amit Praseed Classification November 5, 2019 6 / 22
  • 7. The Perceptron −2 −1 1 2 −2 −1 1 2 Point:(1,1) Weighted Input = 1x0+1x1+1x0.5=2.5>0 Activation: 1 (Correct Classifi- cation) Action: Do Nothing Amit Praseed Classification November 5, 2019 7 / 22
  • 8. The Perceptron −2 −1 1 2 −2 −1 1 2 Point: (2,-2) Weighted Input=1x0+1x2+ (-2)(0.5)=1>0 Activation: 1 (Incorrect Classi- fication) Update weight vectors:  w0 w1 w2   =   0 1 0.5   − η   1 2 −2   =   −0.2 0.6 0.9   Amit Praseed Classification November 5, 2019 8 / 22
  • 9. The Perceptron −2 −1 1 2 −2 −1 1 2 Point: (2,-2) Weighted Input=1x0+1x2+(- 2)(0.5)=1>0 Activation: 1 (Incorrect Classi- fication) Update weight vectors:  w0 w1 w2   =   0 1 0.5   − 0.2   1 2 −2   =   −0.2 0.6 0.9   Amit Praseed Classification November 5, 2019 9 / 22
  • 10. The Perceptron −2 −1 1 2 −2 −1 1 2 Point: (-1,-1.5) Weighted Input=1(-0.2)+ (-1)(0.6)+(-1.5)(0.9)<0 Activation: 0 (Correct Classifi- cation) Action: No Change Amit Praseed Classification November 5, 2019 10 / 22
  • 11. The Perceptron −2 −1 1 2 −2 −1 1 2 Point: (-2,-1) Weighted Input=1(-0.2)+ (-2)(0.6)+(-1)(0.9)<0 Activation: 0 (Correct Classifi- cation) Action: No Change Amit Praseed Classification November 5, 2019 11 / 22
  • 12. The Perceptron −2 −1 1 2 −2 −1 1 2 Point: (-2,1) Weighted Input=1(-0.2)+ (-2)(0.6)+(1)(0.9)=-0.5<0 Activation: 0 (Incorrect Classi- fication) Update weight vectors:  w0 w1 w2   =   −0.2 0.6 0.9   + 0.2   1 −2 1   =   0 0.2 1.1   Amit Praseed Classification November 5, 2019 12 / 22
  • 13. The Perceptron −2 −1 1 2 −2 −1 1 2 Point: (-2,1) Weighted Input=1(-0.2)+ (-2)(0.6)+(1)(0.9)=-0.5<0 Activation: 0 (Incorrect Classi- fication) Update weight vectors:  w0 w1 w2   =   −0.2 0.6 0.9   + 0.2   1 −2 1   =   0 0.2 1.1   Amit Praseed Classification November 5, 2019 13 / 22
  • 14. The Perceptron −2 −1 1 2 −2 −1 1 2 Point: (1.5,-0.4) Weighted Input=1(0)+ (1.5)(0.2)+(-0.4)(1.1)=- 0.14<0 Activation: 0 (Incorrect Classi- fication) Update weight vectors:  w0 w1 w2   =   0 0.2 1.1   + 0.2   1 1.5 −0.5   =   0.2 0.5 1   Amit Praseed Classification November 5, 2019 14 / 22
  • 15. The Perceptron −2 −1 1 2 −2 −1 1 2 Point: (1.5,-0.4) Weighted Input=1(0)+ (1.5)(0.2)+(-0.4)(1.1)=- 0.14<0 Activation: 0 (Incorrect Classi- fication) Update weight vectors:  w0 w1 w2   =   0 0.2 1.1   + 0.2   1 1.5 −0.5   =   0.2 0.5 1   Amit Praseed Classification November 5, 2019 15 / 22
  • 16. A Look Back at the Finale −2 −1 1 2 −2 −1 1 2 Point: (-2,1) Weighted Input=1(-0.2)+ (-2)(0.6)+(1)(0.9)=-0.5<0 Activation: 0 (Incorrect Classi- fication) Update weight vectors:  w0 w1 w2   =   −0.2 0.6 0.9   + 0.2   1 −2 1   =   0 0.2 1.1   Amit Praseed Classification November 5, 2019 16 / 22
  • 17. A Look Back at the Finale −2 −1 1 2 −2 −1 1 2 Point: (-2,1) Weighted Input=1(-0.2)+ (-2)(0.6)+(1)(0.9)=-0.5<0 Activation: 0 (Incorrect Classi- fication) Update weight vectors:  w0 w1 w2   =   −0.2 0.6 0.9   + 0.2   1 −2 1   =   0 0.2 1.1   Amit Praseed Classification November 5, 2019 17 / 22
  • 18. A Look Back at the Finale −2 −1 1 2 −2 −1 1 2 Point: (1.5,-0.4) Weighted Input=1(0)+ (1.5)(0.2)+(-0.4)(1.1)=- 0.14<0 Activation: 0 (Incorrect Classi- fication) Update weight vectors:  w0 w1 w2   =   0 0.2 1.1   + 0.2   1 1.5 −0.5   =   0.2 0.5 1   Amit Praseed Classification November 5, 2019 18 / 22
  • 19. A Look Back at the Finale −2 −1 1 2 −2 −1 1 2 Point: (1.5,-0.4) Weighted Input=1(0)+ (1.5)(0.2)+(-0.4)(1.1)=- 0.14<0 Activation: 0 (Incorrect Classi- fication) Update weight vectors:  w0 w1 w2   =   0 0.2 1.1   + 0.2   1 1.5 −0.5   =   0.2 0.5 1   Amit Praseed Classification November 5, 2019 19 / 22
  • 20. Widrow-Hoff Delta Rule Modifying the weights by the input value during incorrect classification seems excessive, and can lead to the decision boundary swinging back and forth before stabilizing. Intuitively, it is reasonable to modify the weights only by the difference between the threshold and the weighted input. wi (t + 1) = wi (t) + η∆xi (t) ∆ = θ − n i=0 wi ∗ xi Note that in this way, there is no separate equation for the weighted input lying on both sides of the threshold. The sign of ∆ automatically takes care of this. Amit Praseed Classification November 5, 2019 20 / 22
  • 21. Widrow-Hoff Delta Rule −2 −1 1 2 −2 −1 1 2 Point: (-2,1) Weighted Input=1(-0.2)+ (-2)(0.6)+(1)(0.9)=-0.5<0 Activation: 0 (Incorrect Classi- fication) Update weight vectors:  w0 w1 w2   =   −0.2 0.6 0.9   + (0.2)(0 − (−0.5))   1 −2 1   =   −0.1 0.4 1   Amit Praseed Classification November 5, 2019 21 / 22
  • 22. Widrow-Hoff Delta Rule −2 −1 1 2 −2 −1 1 2 Point: (-2,1) Weighted Input=1(-0.2)+ (-2)(0.6)+(1)(0.9)=-0.5<0 Activation: 0 (Incorrect Classi- fication) Update weight vectors:  w0 w1 w2   =   −0.2 0.6 0.9   + (0.2)(0 − (−0.5))   1 −2 1   =   −0.1 0.4 1   Amit Praseed Classification November 5, 2019 22 / 22